Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    listing learning resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     injunction
    0.43
     spectral
    0.42
    ometimes
    0.42
     infrequently
    0.42
     dilig
    0.42
     combiner
    0.41
     vigil
    0.40
     exported
    0.40
    cedented
    0.40
     contends
    0.40
    POSITIVE LOGITS
    Khan
    1.25
     Khan
    1.20
     Tutorials
    0.91
     khan
    0.90
     Learn
    0.90
     YouTube
    0.89
    YouTube
    0.88
     Interactive
    0.88
     tutorials
    0.87
    Learn
    0.86
    Act Density 0.076%

    No Known Activations